INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iven

-0.77

oldown

-0.74

uras

-0.74

inished

-0.65

ensional

-0.64

anan

-0.63

 weap

-0.63

aturday

-0.63

endiary

-0.62

attled

-0.62

POSITIVE LOGITS

wcsstore

0.71

âĢ¦]

0.68

IPS

0.67

 ILCS

0.65

WM

0.64

JA

0.64

ãĤ¦ãĤ¹

0.64

0.63

YR

0.63

Offic

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.